From bbf96a45bafb07bf81d0a966464f93af73f9e876 Mon Sep 17 00:00:00 2001
From: wzdnzd <hanxi2014@gmail.com>
Date: Sun, 10 Nov 2024 10:03:12 +0800
Subject: [PATCH] enhance decode and status check

---
 subscribe/airport.py | 18 ++++++++++++++++--
 subscribe/crawl.py   |  6 +++++-
 2 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/subscribe/airport.py b/subscribe/airport.py
index 6aa4f9753..977a0803f 100644
--- a/subscribe/airport.py
+++ b/subscribe/airport.py
@@ -3,6 +3,7 @@
 # @Author  : wzdnzd
 # @Time    : 2022-07-15
 
+import base64
 import concurrent.futures
 import json
 import os
@@ -622,6 +623,14 @@ def parse(
             )
             return []
 
+    @staticmethod
+    def check_protocol(link: str) -> bool:
+        return re.match(
+            r"^(vmess|trojan|ss|ssr|vless|hysteria|hysteria2|tuic|snell)://[a-zA-Z0-9:.?+=@%&#_\-/]{10,}",
+            utils.trim(link).replace("\r", ""),
+            flags=re.I,
+        )
+
     @staticmethod
     def decode(
         text: str, program: str, artifact: str = "", ignore: bool = False, special: bool = False, throw: bool = False
@@ -647,9 +656,10 @@ def clean_text(document: str) -> str:
         if not text:
             return []
 
+        is_b64encode, is_json = False, False
         if (
-            utils.isb64encode(text)
-            or (text.startswith("{") and text.endswith("}"))
+            (is_b64encode := utils.isb64encode(text))
+            or (is_json := (text.startswith("{") and text.endswith("}")))
             or not re.search(r"^proxies:([\s\r\n]+)?$", text, flags=re.MULTILINE)
         ):
             artifact = utils.trim(text=artifact)
@@ -659,6 +669,10 @@ def clean_text(document: str) -> str:
             v2ray_file = os.path.join(PATH, "subconverter", f"{artifact}.txt")
             clash_file = os.path.join(PATH, "subconverter", f"{artifact}.yaml")
 
+            # base64 encoding if all lines start with valid protocol
+            if not is_b64encode and not is_json and all(AirPort.check_protocol(x) for x in text.split("\n") if x):
+                text = base64.b64encode(text.encode(encoding="UTF8")).decode(encoding="UTF8")
+
             try:
                 with open(v2ray_file, "w+", encoding="UTF8") as f:
                     f.write(text)
diff --git a/subscribe/crawl.py b/subscribe/crawl.py
index 49f5f52a8..eaf3ba5ec 100644
--- a/subscribe/crawl.py
+++ b/subscribe/crawl.py
@@ -1083,7 +1083,7 @@ def extract_subscribes(
         limits, collections, proxies = max(1, limits), {}, []
         sub_regex = r"https?://(?:[a-zA-Z0-9\u4e00-\u9fa5\-]+\.)+[a-zA-Z0-9\u4e00-\u9fa5\-]+(?:(?:(?:/index.php)?/api/v1/client/subscribe\?token=[a-zA-Z0-9]{16,32})|(?:/link/[a-zA-Z0-9]+\?(?:sub|mu|clash)=\d))|https://jmssub\.net/members/getsub\.php\?service=\d+&id=[a-zA-Z0-9\-]{36}(?:\S+)?"
         extra_regex = r"https?://(?:[a-zA-Z0-9\u4e00-\u9fa5\-]+\.)+[a-zA-Z0-9\u4e00-\u9fa5\-]+/sub\?(?:\S+)?target=\S+"
-        protocal_regex = r"(?:vmess|trojan|ss|ssr|snell|hysteria2|vless|hysteria)://[a-zA-Z0-9:.?+=@%&#_\-/]{10,}"
+        protocal_regex = r"(?:vmess|trojan|ss|ssr|snell|hysteria2|vless|hysteria|tuic)://[a-zA-Z0-9:.?+=@%&#_\-/]{10,}"
 
         regex = f"{sub_regex}|{extra_regex}"
 
@@ -1278,6 +1278,10 @@ def check_status(
             yaml.add_multi_constructor("str", lambda loader, suffix, node: str(node.value), Loader=yaml.SafeLoader)
             proxies = yaml.load(content, Loader=yaml.FullLoader).get("proxies", [])
         except:
+            if all(airport.AirPort.check_protocol(x) for x in content.split("\n") if x):
+                return True, False
+
+            # TODO: 如果配置文件为 singbox、quanx、loon、surge等，需要解析出代理节点信息，并判断是否过期
             proxies = []
 
         if proxies is None or len(proxies) == 0: